Knowledge catalogue
arXiv:2606.15517v2 Announce Type: replace Abstract: Large language models often struggle with sensitive prompts. They may refuse outright, provide generic safety boilerplate, or fail to address the us
arXiv:2609.02241v1 Announce Type: new Abstract: Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch acros
arXiv:2609.02255v1 Announce Type: new Abstract: Recent text-to-image models have become increasingly capable of rendering explicit text, but reliable localized text control requires more than generati
arXiv:2609.02852v1 Announce Type: new Abstract: LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanist
arXiv:2609.02421v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planni
Continual learning isn't some fake term but a real goal and arguably one of the most important open ones in 2026. It roughly means: ‘building systems that keep acquiring useful knowledge or skills aft
arXiv:2609.01320v1 Announce Type: new Abstract: Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM tech
arXiv:2603.03146v2 Announce Type: replace-cross Abstract: Integrated communication and computation (IC^2) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) n
arXiv:2609.00242v1 Announce Type: cross Abstract: Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical
arXiv:2609.01161v1 Announce Type: new Abstract: Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce Cop
arXiv:2502.03726v3 Announce Type: replace Abstract: Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these
arXiv:2609.00982v1 Announce Type: cross Abstract: Using a large language model to play the user is now standard in scalable evaluation. It has a repeatedly diagnosed failure: the simulated user is exc
arXiv:2609.00854v1 Announce Type: cross Abstract: Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is s
arXiv:2609.00646v1 Announce Type: new Abstract: Commercial short-drama production follows a multi-stage chain: script, storyboard, keyframe imagery, shot-level video, and the finished short drama. Mos
Fable 5.1 didn't come with document OCR benchmarks, so we benchmarked it on ParseBench: a comprehensive parsing benchmark that's comprised of 2k+ real-world documents across finance, legal, insurance,
arXiv:2609.00659v1 Announce Type: new Abstract: Cooperative perception allows a drone fleet to combine observations from multiple viewpoints. However, existing systems typically fix their feature-shar
arXiv:2609.01422v1 Announce Type: new Abstract: Post-training large language models usually applies a single training recipe to all samples, even though the model's own rollouts reveal different sampl
arXiv:2609.01433v1 Announce Type: new Abstract: Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semanti
arXiv:2609.01560v1 Announce Type: cross Abstract: We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as
I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4
arXiv:2609.01383v1 Announce Type: new Abstract: Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic,
arXiv:2609.01361v1 Announce Type: new Abstract: Linear classifiers trained on hidden states of a large language model (LLM), linear probes, can flag factual errors from a single forward pass. Geometri
arXiv:2609.00491v1 Announce Type: new Abstract: Communicating across cultures is inherently challenging, especially through culturally dense and ambiguous formats like memes. While people expect large
meta, the frontier ai lab? 1/ today we’re releasing muse spark 1.3—available in muse code & the meta model api. this is our most capable model yet—frontier performance almost too cheap to meter. much
arXiv:2609.00734v1 Announce Type: new Abstract: Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence
arXiv:2609.00015v1 Announce Type: new Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, controll
arXiv:2510.03784v2 Announce Type: replace Abstract: Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remain
arXiv:2609.00958v1 Announce Type: new Abstract: We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler
arXiv:2609.00049v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ metho
arXiv:2608.28652v1 Announce Type: new Abstract: Artificial intelligence (AI) models have demonstrated remarkable capabilities across various domains, yet their widespread deployment is impeded by sign
arXiv:2608.29702v1 Announce Type: new Abstract: A token-embedding table holds a hub of short rows near its origin, and we show that this cluster biases what nearest-neighbor intrinsic-dimension (ID) e
arXiv:2601.06022v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding b
arXiv:2607.09600v2 Announce Type: replace Abstract: Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. Howev
Anthropic says its newest AI models, Fable 5.1 and Mythos 5.1, address criticisms from customers about price, data retention, and overzealous safeguards. The company claims Claude Fable 5.1 offers str
Anthropic: Anthropic unveils Claude Fable 5.1, which is generally available, and Mythos 5.1, for trusted partners and with cybersecurity and life sciences safeguards — We're introducing Claude Fable 5
arXiv:2608.29378v1 Announce Type: cross Abstract: Arabic large language models must refuse harmful prompts without over-refusing benign or sensitive prompts, yet a single refusal rate hides this trade
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva
arXiv:2608.30175v1 Announce Type: new Abstract: Peptide-protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets
arXiv:2608.29804v1 Announce Type: new Abstract: Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation met
arXiv:2608.30110v1 Announce Type: cross Abstract: Nowcasting headline macroeconomic indicators, i.e., estimating an indicator's value for the current reference period before its official release, is c
arXiv:2608.29284v1 Announce Type: new Abstract: Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-re
arXiv:2608.29934v1 Announce Type: new Abstract: KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may
arXiv:2608.29970v1 Announce Type: new Abstract: Artistic Text Recognition (ATR) remains challenging because word images often combine decorative fonts, curved layouts, object-like characters, clutter,
arXiv:2608.28631v1 Announce Type: new Abstract: An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model fam
arXiv:2608.28843v1 Announce Type: cross Abstract: We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output or
arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants and
arXiv:2601.18486v3 Announce Type: replace Abstract: Demographic cue-based evaluation is widely used to study how large language models (LLMs) adapt their responses to signaled demographic attributes w
arXiv:2608.29252v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is increasingly used to strengthen the reasoning abilities of large models, yet its effectiveness is bound by how traini
arXiv:2608.29177v1 Announce Type: new Abstract: The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. Ho
arXiv:2608.30730v1 Announce Type: cross Abstract: Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies
arXiv:2602.23188v2 Announce Type: replace Abstract: We propose an efficient retraining strategy for a parameterized Reduced Order Model (ROM) that attains accuracy comparable to full retraining while
arXiv:2608.29281v1 Announce Type: new Abstract: Natural images concentrate their detail in a small fraction of the frame, yet diffusion models spend a full token on every patch, in every layer and at
arXiv:2608.29543v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, ofte
arXiv:2608.31014v1 Announce Type: new Abstract: Computational mental health screening using multimodal speech and text has shown great promise. However, existing models often assume all clinical speec
arXiv:2608.28662v1 Announce Type: new Abstract: Fracture detection and its clinical interpretability see notable improvements when deep vision models are integrated with agentic AI architectures. Whil
arXiv:2608.28611v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) like ChatGPT and LLaMA have transformed AI-driven education, but these systems are predominantly train
arXiv:2503.04822v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many
arXiv:2608.31053v1 Announce Type: new Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation comput
arXiv:2608.30025v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguis
arXiv:2608.30226v1 Announce Type: new Abstract: Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. Ho